photonic_sorcerer@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 1 year agoOutcry from big AI firms over California AI “kill switch” billarstechnica.comexternal-linkmessage-square49fedilinkarrow-up1266arrow-down16
arrow-up1260arrow-down1external-linkOutcry from big AI firms over California AI “kill switch” billarstechnica.comphotonic_sorcerer@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 1 year agomessage-square49fedilink
minus-squarenifty@lemmy.worldlinkfedilinkEnglisharrow-up11·1 year agoSmall problem though: researchers have already found ways to circumvent LLM off-limit queries. I am not sure how you can prevent someone from asking the “wrong” question. It makes more sense for security practices to be hardened and made more robust
Small problem though: researchers have already found ways to circumvent LLM off-limit queries. I am not sure how you can prevent someone from asking the “wrong” question. It makes more sense for security practices to be hardened and made more robust